Spices – Sea Ice Edge Maps From The Kara Sea

• Main Authors: Babiker, Mohamed, Korosov, Anton, Park, Jeong-Won, Hamre, Torill, Yamakawa, Asuka
• Format: Dataset
• Language: English
• Published: Zenodo 2018
• Subjects: Sea ice, Arctic, Sentinel-1, SAR, synthetic aperture radar, Support Vector Machine; Arctic; Kara Sea; Sea ice
• Online Access: https://dx.doi.org/10.5281/zenodo.1310855; https://zenodo.org/record/1310855

Sea ice edge maps derived from Sentinel-1 SAR dual polarisation EW images using a Support Vector Machine (SVM) algorithm. This algorithm is based on a SVM approach, and in addition uses texture calculation and principal component analysis (PCA) to classify sea ice types (Korosov et al., 2016). The main steps of the algorithms include: (1) pre-processing of the raw SAR data, (2) calculation of texture features, (3) unsupervised pre-classification of the image using PCA and k-means cluster analysis to reduce the number of ice classes, (4) expert re-classification of the image into the pre-calculated classes, (5) training of the SVM using input from the previous step, and (6) classifying the full image into the reduced number of classes using the trained SVM. To generate an ice edge product, the SVM algorithm is used with only two classes: sea ice and open water. Korosov, A., N. Zakhvatkina, A. Vesman, A. Mushta, and S. Muckenhuber, Sea ice classification algorithm for Sentinel-1 images, Poster at ESA Living Planet Symposium 2016, Prague, Czech Republic, 9-13 may, 2016.